Category

Agent frameworks & infrastructure

46,465 agents

Every agent in Agent frameworks & infrastructure, page 256 of 465

prompt-evaluator★ 2

Structural prompt analysis + output testing + rewriting. Model-agnostic via LiteLLM. FastAPI service.

CodeLlama-7B-KStack-GGUF★ 2

gguf code text-generation dataset:JetBrains/KStack base_model:JetBrains/CodeLlama-7B-KStack base_model:quantized:JetBrains/CodeLlama-7B-KStack

OBSIDIAN-9B-Coder★ 2

gguf qwen3_5 code coding coder qwen

Qwen1.5-110B-Chat-GGUF★ 2

gguf chat text-generation en license:other endpoints_compatible

Agent-Creator★ 2

Agent-Creator is a framework for building and experimenting with multi-agent systems powered by Microsoft’s AutoGen. The project demonstrates how autonomous AI agents can collaborate, communicate, and solve tasks in a simulated environment. The main file world.py acts as the orchestrator, defining agent behaviors, interactions, and workflows.

wixie★ 2

Self-healing prompt engineering. Autonomously test, converge, and translate prompts across 447 AI models.

swarm_ai★ 2

Python toolkit for parallel Claude and LLM agent orchestration with local state: consensus voting, stigmergy, and boss-worker workflows

Voterpool★ 2

Voterpool is an open-source consensus layer for AI-agents

LFM2.5-1.2B-hermes-agent★ 2

transformers safetensors lfm2 text-generation instruct chatml

qwen3.8-9b-hermes-function-calling-v1-GGUF★ 2

gguf qwen3.5 rocmfpx function-calling text-generation base_model:JamieBradfield/qwen3.8-9b-hermes-function-calling-v1

nook★ 2

Nook is a progression system for AI agents. Verified work generates immutable sparks that evolve your agents over time

memory-palace★ 2

Event-based long-term memory for LLM agents — associative surfacing over query RAG. Closed-loop episodic events, budgeted injection, tiered forgetting. Claude Code hooks + DeepSeek Harness plugin, one shared .memory/ format.

better-harnesses-smaller-models★ 2

Chain-of-density study of 'Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation' (Yang, Zhao, Wu & Kästner 2026, CMU, arXiv:2607.08938) - five-tier note, locator-verified. SLM agents, meta-agent harness optimization.

spotlight★ 2

Agentic AI framework for existing frontend apps — turn natural language into real product actions with typed tools, skills, LangGraph, RAG, memory, and framework-agnostic integrations.

Noetrium★ 2

Noetrium: Reproducible Research Infrastructure for AI Agents - experiments, models, environments, evidence, recovery, evaluation, and verification.

token-prompt-compiler★ 2

Compile human language into token-efficient machine-readable task packets for LLM agents

Local-LLM-Hardware-Explorer★ 2

static region:us

MiniCpm5-Agent★ 2

transformers safetensors llama text-generation mergekit merge

book-openclaw★ 2

OpenClaw 源码解析 — 现代 Agent 系统架构

engram★ 2

🧠 Persistent memory for AI agents. Scan logs, extract learnings via LLM, update long-term memory. Review, reflect, remember.

eihai-releases★ 2

EiHAI builds

Gemma-4-blr★ 2

On-device AI utility assistant powered by Gemma + LiteRT-LM with Wikipedia summarization and QR code generation.

openclaw-lowmem-optimization★ 2

OpenClaw low-memory optimization guide for resource-constrained servers (2GB RAM)

MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16★ 2

transformers safetensors llama text-generation minicpm minicpm5

Qwen3-Coder-30B-A3B-Instruct-3bit★ 2

mlx safetensors qwen3_moe text-generation conversational base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct

Llama-68M-Chat-v1-GGUF★ 2

gguf text-generation ggml quantized q2_k q3_k_m

ai-agents-in-depth★ 2

《深入理解 AI Agent》工程方法论蒸馏 Skill:39 张能力卡,1 个入口,三重验证+盲测 48/48

NOMAD★ 2

empirical research framework designed to analyze multi-agent Large Language Model (LLM) conversations as observable, continuous-state dynamical systems.

self-hosted★ 2

Self-hosted deployment for PlanVault — governed AI agent execution runtime. Docker Compose stack, signed images, Cosign verification, single-tenant VPC deployment.

iac★ 2

Message board for LLM agents on one machine: one C binary, a plain-text log, and a recv that wakes on inotify instead of polling. Zero-token idle. A blackboard, not a broker.

vibermate★ 2

Local traffic runtime for Claude Code and Codex — capture, route, transform, and inspect AI provider traffic on macOS.

FileContext★ 2

Storage-backed file tools and Markdown knowledge-graph context for Microsoft Agent Framework

deepseek-harness-portal★ 2

A multi-tenant platform that provisions and routes isolated DeepSeek Harness (dsh) instances — one container per user.

blok★ 2

Native desktop chat platform — Discord-like, but self-hosted on your own Supabase. Rust P2P voice/video, an AI assistant that runs your server, realtime translation, and a loot-box economy. Tauri 2 + React + Supabase.

ollama-private-llm★ 2

gradio region:us

PhoGPT-4B-Chat-GGUF★ 2

gguf text-generation vi base_model:vinai/PhoGPT-4B-Chat base_model:quantized:vinai/PhoGPT-4B-Chat license:other

dsh-petrinet★ 2

Workflow-net runtime for DeepSeek Harness: resource-aware concurrency, native loops and fan-out, static soundness checking before a plan becomes durable, and process mining over its own event log.

capri-fe★ 2

Grok Build Web UI

vv-agent★ 2

A lightweight agent framework for production runtime. Cycle-based execution with pluggable LLM backends, tool dispatch, memory compression, and distributed scheduling.

minicode★ 2

基于 Claude Code 架构精简的 AI Agent 框架 | 7层架构 Agentic Loop + 6个内置工具 + 三级权限控制 + 动态System Prompt | 可以更加详细的学习工程级架构,也可以自定义内置工具使用

ael-learn-opencode-course★ 2

Learn OpenCode — From Zero to Professional. Interactive course with 6 modules, 17+ lessons, 5 hands-on projects. Agentic coding with MCP, rules, custom agents, skills, and free AI models. Built by Ayman Elmasry — AEL Digital Studio.

eventboat★ 2

Go engine for DAG-based event routing: fan-in/out, backpressure, retry/DLQ, and observability built in.

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF★ 2

gguf gemma4 coding agentic terminal tool-use

wicara-56m-chat★ 2

transformers safetensors llama text-generation wicara pytorch

zyr3-v1★ 2

transformers safetensors zyr3 text-generation qwen qwen2.5

Gemma-4-12B-agentic-abliterated-GGUF★ 2

gguf quantized gemma gemma4 agentic abliterated

Nexusflow.Athene-V2-Agent-GGUF★ 2

gguf text-generation base_model:Nexusflow/Athene-V2-Agent base_model:quantized:Nexusflow/Athene-V2-Agent endpoints_compatible region:us

gemma-4-12b-asterion-agentic★ 2

transformers safetensors gemma4_unified image-text-to-text gemma4 sft

CodeLlama-13B-Instruct-GGUF★ 2

transformers gguf llama text-generation llama-2 code

true-memory-fragments★ 2

Prevent AI coding agents from acting on stale code context with source-aware freshness checks and hard stale gates.

scaling-rl-for-llms-amd-ai-dev-day★ 2

static rl-environment region:us

Qwen3.8-27B-OBLITERATED-Mythos-Class-Agentic★ 2

safetensors qwen3_5 qwen qwen3.8 abliterated uncensored

Hemlock2-Coder-7B-i1-GGUF★ 2

transformers gguf merlina grimoire text-generation orpo

dsv4-behavior-bench★ 2

DSV4 behavior-discrimination benchmark: 81 lightweight zero-dependency pytest grading tests (d10/d11/d12/t2/t3/t4/v4) for datapipe — discriminates harness/agent/persona effects that public tests saturate on

echo-agent★ 2

A persistent agent runtime and its official CLI. Three packages: @echo-agent/core (runtime/SDK, zero runtime dependencies), echo-agent (CLI and interactive TUI), and echo-coding (the coding-agent product).

losp★ 2

losp - a streaming programming language specifically designed for LLM structured metacognition. It is influenced by Lisp, FORTH, brainfuck, Perl but with a healthy dose of novelty.

NDK-SDK-py★ 2

Natural-language tool calling for LLM agents — Python implementation of the NLT paper (arXiv:2510.14453). Boosts tool-calling accuracy on weak/free-tier models by up to 14%.

Cognitive-Friction-Toolkit★ 2

No Promises Without Proof. A dependency-free discipline that forces agents to pair every success claim with evidence and a proof state (OBSERVED/INFERRED/UNVERIFIED/BLOCKED), then derives the completion verdict deterministically.

Khala-Orchestrator-Core★ 2

🤖 AI Agent Teams 2026: Build & Deploy Autonomous AI Systems 🚀

ChatBot-in-LangGraph★ 2

Stateful conversational AI agent built with LangGraph, SQLite, and Streamlit. Features dynamic ReAct tool-calling loops, multi-thread session persistence via SqliteSaver, and 4-bit NF4 quantized local inference (Qwen 2.5) optimized for low-VRAM deployment.

Complete-CrewAI★ 2
skillforge★ 2

面向长任务的 Agent Harness 与受控技能自进化框架。基于 Asyncio ReAct 与 stdio MCP,实现任务状态驱动的上下文治理、业务断言 Oracle、有界修补与防退化版本晋升。

nanocodana★ 2

A tiny but mighty agent that runs in your browser, on your phone, or at the edge.

llmops-telemetry-command-center★ 2

docker streamlit plotly llmops observability telemetry evaluation model-monitoring

llm-zero-gpu-playground★ 2

gradio mcp-server region:us

ZYR3.1MoE★ 2

transformers safetensors qwen3_5_text text-generation merged multi-agent

driaforall.Dria-Agent-a-3B-GGUF★ 2

gguf text-generation base_model:driaforall/Dria-Agent-a-3B base_model:quantized:driaforall/Dria-Agent-a-3B endpoints_compatible region:us

qwen3.8-9b-hermes-fc-tooluse-GGUF★ 2

gguf qwen3.5 function-calling tool-use qlora finetune

Llama-3-Trendyol-LLM-8b-chat-v2.0-GGUF★ 2

gguf text-generation tr license:llama3 endpoints_compatible region:us

Trendyol-LLM-7b-chat-dpo-v1.0-GGUF★ 2

transformers gguf trendyol llama-2 turkish text-generation

Atlas-Chat-9B-GGUF★ 2

transformers gguf conversational text-generation ar dataset:MBZUAI-Paris/Darija-SFT-Mixture

neural-chat-7b-v3-1-GGUF★ 2

gguf LLMs mistral Intel text-generation en

mnemosyne-multimodal-v4★ 2

safetensors mnemosyne cognitive-ai sclm audio text-generation

LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v2-GGUF★ 2

hermes gguf duo-neural llama.cpp agentic coding

Qwen3.8-9B-Function-Calling-xLAM-Unsloth-GGUF★ 2

gguf llama.cpp quantized unsloth lora trl

pi-ultra-scout★ 2

A pi agentic extension that stops weak local LLMs from confidently hallucinating. Auto-dispatches a web-browsing librarian sub-agent to verify API defaults, flags, versions & docs from live sources, returning cited evidence. Works with llama.cpp / Ollama. No cloud required.

deepseek-harness-lazy-capability★ 2

梁神按需模式 / LiangShen Lazy — DeepSeek Harness 的按需工具隔离 preset:默认极简,需要什么能力才临时开放什么,用完自动收回。A minimal-by-default, capability-on-demand agent preset for DeepSeek Harness.

No-More-Agents-Dot-MD★ 2

Context at the right moment — not always. No More Agents Dot MD replaces the monolithic AGENTS.md with tiny, security first and declarative context files.

aglyphs★ 2

Compact symbolic notation for Grok-powered agentic systems

claude-code-ultimate-guide★ 2

🌐 Discover clear guidance and templates for using Claude effectively, enhancing your coding skills and productivity through engaging quizzes and resources.

AgentX★ 2

AI-powered framework for building voice-enabled, context-aware assistants with LangChain, OpenAI GPT, FAISS vector search & Vosk speech recognition. Modular design for document retrieval, conversational memory & workflow automation.

MfkAgent★ 2

真正具备工程闭环交付与工业审美的本地多智能体协作与自主开发桌面工作站

prometheus-ai-orchestrator★ 2

Chrome extension that orchestrates multiple AI chatbots (ChatGPT, DeepSeek, Gemini, Grok, Claude, Qwen) — send one question to all, collect answers, aggregate via expert AI. No API keys needed.

afferent-os★ 2

Concept: an operating environment where AI is not an application but the computer's nervous system — organs, afferent perception, a shared scene of state.

atflows★ 2

AtFlows is a local observability tool for LLM applications. Point your SDK at it, see your costs, tokens, and latency in real-time.

omo-model-configurator★ 2

Find the best and newest models for oh-my-openagent (OMO) configurations using Artificial Analysis data

memory-engineering★ 2

Event-Driven Cognitive Execution Engine for AI Agents — 612 lines of pure Python, zero dependencies. BM25 retrieval + 5-type classifier + negation detection. Deployed in production for CiteFlow's 3 AI Agents.

omegaclaw-deontic★ 2

Deontic Task Orchestrator for OmegaClaw. Has defeasible event calculus, deontic and temporal reasoning, and agent verifiable work system

FIDEL-Agents★ 2

A benchmark measuring AI agent reliability on paired Amharic and English tasks in simulated Ethiopian workflows.

LLM-Cost-Optimizer-2026---Reduce-Token-Usage-by-75-AI-Efficiency-Software★ 2

Smart LLM and cloud code optimization tool that cuts token costs by up to 75%. Perfect for AI developers seeking maximum efficiency and lower expenses in 2026.

deepseek-peak-tray-indicator★ 2

DeepSeek API peak/off-peak pricing tray app & alerts (Win/Mac)

llm-api-converter★ 2

A GOST Rewriter HTTP plugin that converts bidirectionally between OpenAI Chat Completions and Anthropic Messages API formats

Qwen-7B-toolcalling-ReSearch-gguf-Q8_0-codex★ 2

transformers gguf qwen2 text-generation function-calling tool-calling

dolphin-llama3-8B-sleeper-agent-standard-lora★ 2

transformers safetensors llama text-generation conversational arxiv:1910.09700

evolvebank★ 2

Self-evolving agent memory that distills, retrieves, and evaluates reusable reasoning strategies.

Boris★ 2

A working AI agent built in C from scratch — no frameworks, no SDK. ReAct loop, tool system, filesystem sandboxing, 200+ tests.

agent-harness-core★ 2

Self-hosted Python agent runtime for Linux with Telegram, Discord and CLI; durable conversations, tasks, workspaces, memory, tools and delivery through an AHC-managed Codex backend. Pre-release.

LLMs_for_Agent_Planning★ 2

Thesis Project - Exploring the Use of LLMs for Agent Planning with a focus on logprob-based uncertainty

ru-prop-management-eval★ 2

How modern LLMs answer russian property management questions?

team6-kit★ 2

Build a team of AI agents that work together under clear rules: one agent plans, one builds, one checks. Includes ready-made agent profiles and a builder script.

Other categories